© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 746
    Prev
    Next
    INDEX
    Explanations

    references to a specific character code or type, particularly "Ch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rist
    -0.32
    adelphia
    -0.29
    UpInside
    -0.28
    inese
    -0.26
    nowled
    -0.25
    elsea
    -0.25
    icago
    -0.25
    arLayout
    -0.25
    mission
    -0.25
    urch
    -0.24
    POSITIVE LOGITS
    aos
    0.19
    emin
    0.17
    oi
    0.16
    er
    0.15
    nen
    0.15
    adiator
    0.15
    pared
    0.15
    ose
    0.15
    thin
    0.15
    aat
    0.15
    Activations Density 0.020%

    No Known Activations